Getting the Most Out of Agents Without Trusting Them Blindly — Design Patterns for Agentic AI in Regulated Financial Systems

#philadelphia, #september#ieee #AI
Share

IEEE Section Night Webinar

Webinar link and password will be forwarded to all registered participants after Noon on the day of the meeting. Check your spam folder if you don't see the email. 

Webinar is open to all.

Getting the Most Out of Agents Without Trusting Them Blindly — Design Patterns for Agentic AI in Regulated Financial Systems

This talk is about using agentic AI correctly in regulated systems — places where a mistake isn't just a bug, it's a compliance or financial exposure. Three real-world, before-and-after cases: consolidating custodian data pipelines feeding trading and portfolio systems, resolving customer identity across the globe with a multi-agent design, and speeding up loan sanctioning with a lightweight triage agent. Each one shows where agentic AI genuinely earns its cost and where a simpler, deterministic check already wins.

The throughline is a governance-first pattern: agents propose, but a validation layer, compliance rule, or human always makes the final call, and a model is only invoked when a cheaper check has already failed. Attendees will leave with a practical way to think about using agentic AI in their own regulated or high-stakes systems, including a tiered, cost-conscious approach to introducing LLMs, a self-healing pattern that resolves repeated pipeline failures automatically, and a clear-eyed way to decide when a multi-agent design is worth its added complexity.

Learning objectives

  1. Apply these patterns to real scenarios to cut manual effort and prevent token over-usage while getting the most from agentic AI.
  2. Decide when a task actually needs an LLM versus a cheaper, faster check.
  3. Build a pipeline that remembers its own failures, so repeat errors resolve automatically.
  4. Judge when a multi-agent design is worth it — and when one agent, or none, is enough.

 


  Date and Time

  Location

  Hosts

  Registration


  • Add_To_Calendar_icon Add Event to Calendar

Loading virtual attendance info...

  • Contact Event Host
  • Starts 02 September 2026 04:00 AM UTC
  • Ends 15 September 2026 04:00 PM UTC
  • Admission fee ?

  Speakers

Anubhuti Singh of Enterprise Architect, Macquarie Group

Topic:

Getting the Most Out of Agents Without Trusting Them Blindly — Design Patterns for Agentic AI in Regulated Financial Sys

Biography:

Anubhuti Singh is an Enterprise Architect and engineer with over 15 years of experience designing large-scale data infrastructure for the financial services industry, including five years as a Principal Data Engineer and Solutions Architect at institutions including Macquarie Asset Management, Fidelity Investments, and LendingClub. Her work focuses on cloud-native data architecture, real-time data pipelines, and most recently the practical application of agentic AI within regulated environments. She holds a Master's degree in Computer Science from the University of Louisville. Her work has also touched agriculture-tech and ad-tech, building geolocation-based targeting systems using public, aggregated data.

Address:United States




Agenda

WEBINAR: 7:00 - 8:00 P.M. 

The Zoom Webinar link and password will be forwarded to all registered participants after Noon on the day of the meeting. Check your spam folder if you don't see the email. 

Webinar is open to all.

PDH certificates are available and an evaluation form will be emailed to you after the meeting. PDH certificate are sent by IEEE USA 3-4 weeks after the meeting.